Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4094 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1948486 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4336. Min Act: -0.0000

Data Index: 979983 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1472180 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.4530. Min Act: -0.0000

Data Index: 1709325 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1986265 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1967. Min Act: -0.0000

Data Index: 178450 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1874595 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1860502 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1674340 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1307139 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1309959 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1074596 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1373000 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.1194. Min Act: -0.0000

Data Index: 14893 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.0916. Min Act: -0.0000

Data Index: 1442410 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2187. Min Act: -0.0000

Data Index: 740864 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.0852. Min Act: -0.0000

Data Index: 929313 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 1.7014. Min Range: -1.7014

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1800826 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.7014. Min Range: -1.7014

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1542641 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 1.7014. Min Range: -1.7014

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1244575 (The Pile)

Max Activating Token Index: 902